Generative Adversarial Networks and Image Synthesis

Latest papers

• MemCam: Memory-Augmented Camera Control for Consistent Video Generation

  Xinhang Gao, Junlin Guan, Shuhan Luo, Wenzhuo Li, Guanghuan Tan, Jiacheng Wang · 30 March 2026

  Interactive video generation has significant potential for scene simulation and video creation. However, existing methods often struggle with maintaining scene consistency during long video generation under dynamic camera control due to limited contextual information. To address this challenge, we p…

• Generation Is Compression: Zero-Shot Video Coding via Stochastic Rectified Flow

  Ziyue Zeng, Xun Su, Haoyuan Liu, Bingyu Lu, Yui Tatsumi, Hiroshi Watanabe · 30 March 2026

  Existing generative video compression methods use generative models only as post-hoc reconstruction modules atop conventional codecs. We propose \emph{Generative Video Codec} (GVC), a zero-shot framework that turns a pretrained video generative model into the codec itself: the transmitted bitstream …

• DiReCT: Disentangled Regularization of Contrastive Trajectories for Physics-Refined Video Generation

  Abolfazl Meyarian, Amin Karimi Monsefi, Rajiv Ramnath, Ser-Nam Lim · 30 March 2026

  Flow-matching video generators produce temporally coherent, high-fidelity outputs yet routinely violate elementary physics because their reconstruction objectives penalize per-frame deviations without distinguishing physically consistent dynamics from impossible ones. Contrastive flow matching offer…

• When Identities Collapse: A Stress-Test Benchmark for Multi-Subject Personalization

  Zhihan Chen, Yuhuan Zhao, Yijie Zhu, Xinyu Yao · 30 March 2026

  Subject-driven text-to-image diffusion models have achieved remarkable success in preserving single identities, yet their ability to compose multiple interacting subjects remains largely unexplored and highly challenging. Existing evaluation protocols typically rely on global CLIP metrics, which are…

• PhysVid: Physics Aware Local Conditioning for Generative Video Models

  Saurabh, Pathak, Elahe Arani, Mykola Pechenizkiy, Bahram Zonooz · 30 March 2026

  Generative video models achieve high visual fidelity but often violate basic physical principles, limiting reliability in real-world settings. Prior attempts to inject physics rely on conditioning: frame-level signals are domain-specific and short-horizon, while global text prompts are coarse and no…

• DRiffusion: Draft-and-Refine Process Parallelizes Diffusion Models with Ease

  Runsheng Bai, Chengyu Zhang, Yangdong Deng · 30 March 2026

  Diffusion models have achieved remarkable success in generating high-fidelity content but suffer from slow, iterative sampling, resulting in high latency that limits their use in interactive applications. We introduce DRiffusion, a parallel sampling framework that parallelizes diffusion inference th…

• A-SelecT: Automatic Timestep Selection for Diffusion Transformer Representation Learning

  Changyu Liu, James Chenhao Liang, Wenhao Yang, Yiming Cui, Jinghao Yang, Tianyang Wang, Qifan Wang, Dongfang Liu, Cheng Han · 30 March 2026

  Diffusion models have significantly reshaped the field of generative artificial intelligence and are now increasingly explored for their capacity in discriminative representation learning. Diffusion Transformer (DiT) has recently gained attention as a promising alternative to conventional U-Net-base…

• Enhancing Efficiency and Performance in Deepfake Audio Detection through Neuron-level Dropin & Neuroplasticity Mechanisms

  Yupei Li, Shuaijie Shao, Manuel Milling, Bj\"orn Schuller · 27 March 2026

  Current audio deepfake detection has achieved remarkable performance using diverse deep learning architectures such as ResNet, and has seen further improvements with the introduction of large models (LMs) like Wav2Vec. The success of large language models (LLMs) further demonstrates the benefits of …

• Light Cones For Vision: Simple Causal Priors For Visual Hierarchy

  Manglam Kartik, Neel Tushar Shah · 27 March 2026

  Standard vision models treat objects as independent points in Euclidean space, unable to capture hierarchical structure like parts within wholes. We introduce Worldline Slot Attention, which models objects as persistent trajectories through spacetime worldlines, where each object has multiple slots …

• MedShift: Implicit Conditional Transport for X-Ray Domain Adaptation

  Francisco Caetano, Christiaan Viviers, Peter H. N. de With, Fons van der Sommen · 27 March 2026

  Synthetic medical data offers a scalable solution for training robust models, but significant domain gaps limit its generalizability to real-world clinical settings. This paper addresses the challenge of cross-domain translation between synthetic and real X-ray images of the head, focusing on bridgi…

• Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models

  Kaijin Chen, Dingkang Liang, Xin Zhou, Yikang Ding, Xiaoqiang Liu, Pengfei Wan, Xiang Bai · 27 March 2026

  Video world models have shown immense potential in simulating the physical world, yet existing memory mechanisms primarily treat environments as static canvases. When dynamic subjects hide out of sight and later re-emerge, current methods often struggle, leading to frozen, distorted, or vanishing su…

• Scalable High-Resolution Pixel-Space Image Synthesis with Hourglass Diffusion Transformers

  Katherine Crowson, Stefan Andreas Baumann, Alex Birch, Tanishq Mathew Abraham, Daniel Z. Kaplan, Enrico Shippole · 27 March 2026

  We present the Hourglass Diffusion Transformer (HDiT), an image generative model that exhibits linear scaling with pixel count, supporting training at high-resolution (e.g. $1024 \times 1024$) directly in pixel-space. Building on the Transformer architecture, which is known to scale to billions of p…

• MoireMix: A Formula-Based Data Augmentation for Improving Image Classification Robustness

  Yuto Matsuo, Yoshihiro Fukuhara, Yuki M. Asano, Rintaro Yanagi, Hirokatsu Kataoka, Akio Nakamura · 27 March 2026

  Data augmentation is a key technique for improving the robustness of image classification models. However, many recent approaches rely on diffusion-based synthesis or complex feature mixing strategies, which introduce substantial computational overhead or require external datasets. In this work, we …

• PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference

  Xiaofeng Mao, Shaohao Rui, Kaining Ying, Bo Zheng, Chuanhao Li, Mingmin Chi, Kaipeng Zhang · 27 March 2026

  Autoregressive video diffusion models have demonstrated remarkable progress, yet they remain bottlenecked by intractable linear KV-cache growth, temporal repetition, and compounding errors during long-video generation. To address these challenges, we present PackForcing, a unified framework that eff…

• A CDF-First Framework for Free-Form Density Estimation

  Chenglong Song, Mazharul Islam, Lin Wang, Bing Chen, Bo Yang · 27 March 2026

  Conditional density estimation (CDE) is a fundamental task in machine learning that aims to model the full conditional law $\mathbb{P}(\mathbf{y} \mid \mathbf{x})$, beyond mere point prediction (e.g., mean, mode). A core challenge is free-form density estimation, capturing distributions that exhibit…

• Causal-INSIGHT: Probing Temporal Models to Extract Causal Structure

  Benjamin Redden, Hui Wang, Shuyan Li · 27 March 2026

  Understanding directed temporal interactions in multivariate time series is essential for interpreting complex dynamical systems and the predictive models trained on them. We present Causal-INSIGHT, a model-agnostic, post-hoc interpretation framework for extracting model-implied (predictor-dependent…

• SAVe: Self-Supervised Audio-visual Deepfake Detection Exploiting Visual Artifacts and Audio-visual Misalignment

  Sahibzada Adil Shahzad, Ammarah Hashmi, Junichi Yamagishi, Yusuke Yasuda, Yu Tsao, Chia-Wen Lin, Yan-Tsung Peng, Hsin-Min Wang · 27 March 2026

  Multimodal deepfakes can exhibit subtle visual artifacts and cross-modal inconsistencies, which remain challenging to detect, especially when detectors are trained primarily on curated synthetic forgeries. Such synthetic dependence can introduce dataset and generator bias, limiting scalability and r…

• SPARE: Self-distillation for PARameter-Efficient Removal

  Natnael Mola, Leonardo S. B. Pereira, Carolina R. Kelsch, Luis H. Arribas, Juan C. S. M. Avedillo · 26 March 2026

  Machine Unlearning aims to remove the influence of specific data or concepts from trained models while preserving overall performance, a capability increasingly required by data protection regulations and responsible AI practices. Despite recent progress, unlearning in text-to-image diffusion models…

• Tutor-Student Reinforcement Learning: A Dynamic Curriculum for Robust Deepfake Detection

  Zhanhe Lei, Zhongyuan Wang, Jikang Cheng, Baojin Huang, Yuhong Yang, Zhen Han, Chao Liang, Dengpan Ye · 26 March 2026

  Standard supervised training for deepfake detection treats all samples with uniform importance, which can be suboptimal for learning robust and generalizable features. In this work, we propose a novel Tutor-Student Reinforcement Learning (TSRL) framework to dynamically optimize the training curricul…

• Sparse Autoencoders for Interpretable Medical Image Representation Learning

  Philipp Wesp, Robbie Holland, Vasiliki Sideri-Lampretsa, Sergios Gatidis · 26 March 2026

  Vision foundation models (FMs) achieve state-of-the-art performance in medical imaging. However, they encode information in abstract latent representations that clinicians cannot interrogate or verify. The goal of this study is to investigate Sparse Autoencoders (SAEs) for replacing opaque FM image …

• Self-Aware Markov Models for Discrete Reasoning

  Gregor Kornhardt, Jannis Chemseddine, Christian Wald, Gabriele Steidl · 26 March 2026

  Standard masked discrete diffusion models face limitations in reasoning tasks due to their inability to correct their own mistakes on the masking path. Since they rely on a fixed number of denoising steps, they are unable to adjust their computation to the complexity of a given problem. To address t…

• Probabilistic Geometric Alignment via Bayesian Latent Transport for Domain-Adaptive Foundation Models

  Kuepon Aueawatthanaphisut, Kuepon Aueawatthanaphisut · 26 March 2026

  Adapting large-scale foundation models to new domains with limited supervision remains a fundamental challenge due to latent distribution mismatch, unstable optimization dynamics, and miscalibrated uncertainty propagation. This paper introduces an uncertainty-aware probabilistic latent transport fra…

• DreamerAD: Efficient Reinforcement Learning via Latent World Model for Autonomous Driving

  Pengxuan Yang, Yupeng Zheng, Deheng Qian, Zebin Xing, Qichao Zhang, Linbo Wang, Yichen Zhang, Shaoyu Guo, Zhongpu Xia, Qiang Chen, Junyu Han, Lingyun Xu, Yifeng Pan, Dongbin Zhao · 26 March 2026

  We introduce DreamerAD, the first latent world model framework that enables efficient reinforcement learning for autonomous driving by compressing diffusion sampling from 100 steps to 1 - achieving 80x speedup while maintaining visual interpretability. Training RL policies on real-world driving data…

• Policy-based Tuning of Autoregressive Image Models with Instance- and Distribution-Level Rewards

  Orhun Bu\u{g}ra Baran, Melih Kandemir, Ramazan Gokberk Cinbis · 25 March 2026

  Autoregressive (AR) models are highly effective for image generation, yet their standard maximum-likelihood estimation training lacks direct optimization for sample quality and diversity. While reinforcement learning (RL) has been used to align diffusion models, these methods typically suffer from o…

• Guided Star-Shaped Masked Diffusion

  Viacheslav Meshchaninov, Egor Shibaev, Artem Makoian, Ivan Klimov, Nikita Balagansky, Daniil Gavrilov, Aibek Alanov, Dmitry Vetrov · 25 March 2026

  The performance of pre-trained masked diffusion models is often constrained by their sampling procedure, which makes decisions irreversible and struggles in low-step generation regimes. We introduce a novel sampling algorithm that works with pre-trained models and, after a lightweight fine-tuning of…